hugpadhugpad

amazon / GDN-primed-HQwen3-32B-Instruct

Text Generation34B1673Updated Sep 19, 2026
Hugging Face

Downloads

167

Likes

3

Last updated

Sep 19, 2026

License

apache-2.0

GDN-primed-HQwen3-32B-Instruct is a Hybrid language model consisting of 50% Attention layers and 50% Gated DeltaNet (GDN) layers, primed from Qwen3-32B using the Hybrid Model Factory Priming pipeline. The model is instruction-tuned and supports context lengths up to 128K tokens.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • hybrid_qwen3
  • text-generation
  • hybrid
  • ssm
  • state-space-model

Technical specifications

Parameters34B
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen3-32B
Licenseapache-2.0